No abstract

Abstract. In this work, we present a novel approach to mass detection in digital mammograms. The great variability of the masses appearance is the main obstacle of building a mass detection method. It is indeed demanding to characterize all the varieties of masses with a reduced set of features. Hence, in our approach we have chosen not to extract any feature, for the detection of the region of interest; on the contrary, we exploit all the information available on the image. A multiresolution overcomplete wavelet representation is performed, in order to codify the image with redundancy of information. The vectors of the very-large space obtained are then provided to a first SVM classifier. The detection task is here considered as a two-class pattern recognition problem: crops are classified as suspect or not, by using this SVM classifier. False candidates are eliminated with a second cascaded SVM. To further reduce the number of false positives, an ensemble of experts is applied: the final suspect regions are achieved by using a voting strategy. The sensitivity of the presented system is nearly 80% with a false-positive rate of 1.1 marks per image, estimated on images coming from the USF DDSM database.

Although neuronal density analysis on human brain slices is available from stereological studies, data on the spatial distribution of neurons in 3D are still missing. Since the neuronal organization is very inhomogeneous in the cerebral cortex, it is critical to map all neurons in a given volume rather than relying on sparse sampling methods. To achieve this goal, we implement a new tissue transformation protocol to clear and label human brain tissues and we exploit the high-resolution optical sectioning of two-photon fluorescence microscopy to perform 3D mesoscopic reconstruction. We perform neuronal mapping of 100mm3 human brain samples and evaluate the volume and density distribution of neurons from various areas of the cortex originating from different subjects (young, adult, and elderly, both healthy and pathological). The quantitative evaluation of the density in combination with the mean volume of the thousands of neurons identified within the specimens, allow us to determine the layer-specific organization of the cerebral architecture.

The classification of tumoral masses and normal breast tissue is targeted. A mass detection algorithm which does not refer explicitly to shape, border, size, contrast or texture of mammographic suspicious regions is evaluated. In the present approach, classification features are embodied by the image representation used to encode suspicious regions. Classification is performed by means of a support vector machine (SVM) classifier. To investigate whether improvements can be achieved with respect to a previously proposed overcomplete wavelet image representation, a pixel and a discrete wavelet image representations are developed and tested. Evaluation is performed by extracting 6000 suspicious regions from the digital database for screening mammography (DDSM) collected by the University of South Florida (USF). More specifically, 1000 regions representing biopsy-proven tumoral masses (either benign or malignant) and 5000 regions representing normal breast tissue are extracted. Results demonstrate very high performance levels. The area Az under the receiver operating characteristic (ROC) curve reaches values of 0.973 ± 0.002, 0.948 ± 0.004 and 0.956 ± 0.003 for the pixel, discrete wavelet and overcomplete wavelet image representations, respectively. In particular, the improvement in the Az value with the pixel image representation is statistically significant compared to that obtained with the discrete wavelet and overcomplete wavelet image representations (two-tailed p-value < 0.0001). Additionally, 90% true positive fraction (TPF) values are achieved with false positive fraction (FPF) values of 6%, 11% and 7%, respectively.